Interactive Video Corpus Moment Retrieval using Reinforcement Learning
This addresses the challenge of finding hidden video moments in large corpora for users, though it is incremental as it builds on existing reinforcement learning methods for interactive search.
The paper tackles the problem of known-item video search by using reinforcement learning to interactively plan navigation paths based on user feedback, aiming to retrieve hidden targets within a few rounds. Experimental results on TVR and DiDeMo datasets show effectiveness in retrieving moments deep in ranked lists compared to state-of-the-art auto-search engines like CONQUER and HERO.
Known-item video search is effective with human-in-the-loop to interactively investigate the search result and refine the initial query. Nevertheless, when the first few pages of results are swamped with visually similar items, or the search target is hidden deep in the ranked list, finding the know-item target usually requires a long duration of browsing and result inspection. This paper tackles the problem by reinforcement learning, aiming to reach a search target within a few rounds of interaction by long-term learning from user feedbacks. Specifically, the system interactively plans for navigation path based on feedback and recommends a potential target that maximizes the long-term reward for user comment. We conduct experiments for the challenging task of video corpus moment retrieval (VCMR) to localize moments from a large video corpus. The experimental results on TVR and DiDeMo datasets verify that our proposed work is effective in retrieving the moments that are hidden deep inside the ranked lists of CONQUER and HERO, which are the state-of-the-art auto-search engines for VCMR.